AI and models · Independent · 22 Oct 2026

Kiln-AI/Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

← AI and models
Kiln: AI development workbench. Builds, evaluates, and optimizes artificial intelligence systems.

In simple English

Building artificial intelligence tools often requires jumping between many different websites and writing custom code. Kiln brings testing, prompt improvement, and agent building into one local desktop application. Your whole team can rate outputs and add data without writing a single line of code. It connects to your own API keys or runs offline with local models. The desktop app is free to use, with paid features for advanced automation and prompt optimization.

What it is

Kiln is a local-first workbench that handles the full lifecycle of artificial intelligence development from evaluation to deployment. It combines a desktop application for non-technical team members with an open-source Python library for engineers.

What it is good for

Solo builders and small teams who want to test prompts, build retrieval-augmented generation systems, and fine-tune language models without locking their data into a proprietary cloud service.

Stars5.2k
LicenceCustom
Latestv1.2.0 (2026-09-29)checked 22 Oct 2026
Last code change2026-10-22
Written inPython
Setup effort
2 / 5
Payoff
4 / 5
Good
  • Combines testing, prompt optimization, and agent building in one interface.
  • Runs locally on your computer to keep your data under your control.
  • Allows non-programmers to rate outputs and contribute test data.
Watch for
  • Custom licence terms apply to parts of the application rather than standard open source.
  • Advanced features such as the automatic prompt optimizer require a paid subscription.
  • Running local models or large evaluation sets requires significant computer memory and processing power.
Replaces

manual prompt testing in chat windows and scattered python evaluation scripts

Works well with

Ollama

Similar repositories
Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
pip install kiln-ai

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Models & Inference › Model Fine-Tuning.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.